Project laboratory Brain-Computer Interfaces
| Lecturer (assistant) | |
|---|---|
| Duration | 4 SWS |
| Term | Wintersemester 2024/25 |
| Dates | See TUMonline |
Objectives
After participation in this course, the student is able to independently conduct defined research projects related to brain-computer interfaces. This includes:
• performing a literature research with regards to defined subfields in the above given field
• designing experiments that allow testing hypotheses with respect to said field
• conducting experiments to gather neural activity measured both electrically and optically
• analyzing and classifying time-series data using common signal processing techniques and various machine learning approaches
• presenting results orally during biweekly group meetings and in writing in the form of a report
• performing a literature research with regards to defined subfields in the above given field
• designing experiments that allow testing hypotheses with respect to said field
• conducting experiments to gather neural activity measured both electrically and optically
• analyzing and classifying time-series data using common signal processing techniques and various machine learning approaches
• presenting results orally during biweekly group meetings and in writing in the form of a report
Description
Projects are given out based on availability throughout the semester. Please contact Bernhard Wolfrum or George Al Boustani for further info.
The participants will work on up-to-date BCI research projects of the neuroelectronics group. The course will start with a screening of the current literature. Afterwards, the students will work on a defined scientific project within the context of brain-computer interfaces. Specifically, the students will work on topics such as
- design and implementation of EEG and fNIRS experiments
- signal processing techqnieus for neural recording
- classification strategies for the detection of sparse events
- study of motion artifacts
- etc.
The participants will work on up-to-date BCI research projects of the neuroelectronics group. The course will start with a screening of the current literature. Afterwards, the students will work on a defined scientific project within the context of brain-computer interfaces. Specifically, the students will work on topics such as
- design and implementation of EEG and fNIRS experiments
- signal processing techqnieus for neural recording
- classification strategies for the detection of sparse events
- study of motion artifacts
- etc.
Prerequisites
Experience in signal processing and machine learning
Teaching and learning methods
The module will comprise a project lab course. After an introduction to the field, the student will independently carry out state-of-the-art brain-computer interface experiments. The results will be analyzed and discussed with an experienced tutor. This will help the student to design follow-up experiments to reach their scientific goal. Thereby the students will achieve a deeper understanding of the interdisciplinary field of neuroelectronics in a research environment and learn to design, conduct, analyze and present scientific experiments.
The students will present their results in a written report as well as an oral presentation. The integration of students within the research group is fostered by appointing an experienced group member as an additional mentor. This will allow the students to participate at cutting-edge research projects at an early stage of their career.
The students will present their results in a written report as well as an oral presentation. The integration of students within the research group is fostered by appointing an experienced group member as an additional mentor. This will allow the students to participate at cutting-edge research projects at an early stage of their career.
Recommended literature
Liu Y et al. Towards a Hybrid P300-Based BCI Using Simultaneous fNIR and EEG. Foundations of Augmented Cognition: 7th International Conference, AC 2013, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013. Proceedings (pp.335-344)
Khan MJ and Hong KS, Hybrid EEG-fNIRS-based eight-command decoding for BCI: Application to quadrocopter control. Frontiers in Neurorobotics 2017, 11, 6
Fazli S et al. Enhanced performance by a hybdrif NIRS-EEG brain computer interface, NeuroImage 2012, 59, 519-529
Trakoolwilaiwan T. et al. Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer-interface: three-class classification of rest, right-, and left-hand motor execution, Neurophoton. 2017, 5, 1
Lawhern VJ et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. J. Neural Eng. 2018; 1 5: 05601 3
Schirrmeister RT et al. Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 2017; 38: 5391 -5420
Additional project-specific literature will be given at the project start.
Khan MJ and Hong KS, Hybrid EEG-fNIRS-based eight-command decoding for BCI: Application to quadrocopter control. Frontiers in Neurorobotics 2017, 11, 6
Fazli S et al. Enhanced performance by a hybdrif NIRS-EEG brain computer interface, NeuroImage 2012, 59, 519-529
Trakoolwilaiwan T. et al. Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer-interface: three-class classification of rest, right-, and left-hand motor execution, Neurophoton. 2017, 5, 1
Lawhern VJ et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. J. Neural Eng. 2018; 1 5: 05601 3
Schirrmeister RT et al. Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 2017; 38: 5391 -5420
Additional project-specific literature will be given at the project start.